Last active
May 5, 2022 19:57
-
-
Save apoorvalal/e67ab79491835de8af2fd1286154ae7b to your computer and use it in GitHub Desktop.
example of text parsing using gettysburg address.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# %% | |
from bs4 import BeautifulSoup | |
from urllib import request | |
import re | |
from nltk.corpus import stopwords | |
from nltk.stem import PorterStemmer | |
from nltk.tokenize import word_tokenize | |
from collections import Counter | |
# run once | |
# import nltk | |
# nltk.download("stopwords") | |
# %% scrape | |
url = request.urlopen('http://avalon.law.yale.edu/19th_century/gettyb.asp').read() | |
soup = BeautifulSoup(url) | |
# %% bag o'words | |
text = soup.p.contents[0] | |
# drop punctuation | |
text = re.sub(r'[^\w\s]', '', text) | |
# make list by splitting | |
textlist = text.split() | |
# %% drop stopwords | |
textlist = [w.lower() for w in textlist if w not in stopwords.words('english')] | |
# %% lemmatize | |
ps = PorterStemmer() | |
textlist = [ps.stem(w) for w in textlist] | |
# %% count words | |
word_counts = Counter(textlist) | |
word_counts.most_common()[0:10] | |
# %% |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment